case study
Parcel Volume Forecasting
Necessary information /
Context / Client information
DPD needed to verify whether the MyIO platform could accurately forecast parcel volumes across its logistics network. The goal of the PoC was to retrospectively forecast parcel volumes for the first quarter of 2023 and validate forecast accuracy at different levels of detail.
The project worked with approximately 45 million parcels per year, and the forecast needed to cover the hierarchical structure of the logistics network — from the global level through countries and regions down to individual postcode areas.
How we solved the problem /
Solution /
DNAi used the MyIO platform to create a hierarchical forecasting model for parcel volumes.
The system enabled retrospective evaluation of historical data, forecasting of expected parcel volumes, and comparison of model outputs with actual values. The PoC also included model performance monitoring, retrospective evaluation of previous periods, and analysis of changes in time-series dynamics.
Used technologies /
Technologies /
The solution was available in the MyIO cloud platform and focused on accurate forecasting of logistics volumes within a hierarchical network.
- hierarchical parcel volume forecasting at global / country / region / postcode levels
- probabilistic forecasting
- 4-week lead time
- retrospective evaluation of forecast accuracy
- model performance monitoring
- analysis of changes in time-series dynamics
Direct outcome /
RESULT /
The PoC confirmed the ability of the MyIO platform to accurately forecast parcel volumes across a logistics network.
- 45 million parcels per year in the analyzed scope
- 3.9% average global forecast error
- 80% of forecast errors below 5%
The results confirmed the technical feasibility of the solution and its applicability for capacity planning within the logistics network.
contact us
